Abstract: In order to analyze an information signal, a significant short-time spectrum is extracted from the information signal, the means for extracting being configured to extract such short-time spectra which come closer to a specific characteristic than other short-time spectra of the information signal. The short-time spectra extracted are then decomposed into component signals using ICA analysis, a component signal spectrum representing a profile spectrum of a tone source which generates a tone corresponding to the characteristic sought for. From a sequence of short-time spectra of the information signal and from the profile spectra determined, an amplitude envelope is eventually calculated for each profile spectrum, the amplitude envelope indicating how a profile spectrum of a tone source all in all changes over time.

Abstract: An approach to comparing events in word spotting, such as comparing putative and reference instances of a keyword, makes use of a set of models of subword units. For each of two acoustic events and for each of a series of times in each of the events, a probability associated with each of the models of the set of subword units is computed. Then, a quantity characterizing a comparison of the two acoustic events, one occurring in each of the two acoustic signals, is computed using the computed probabilities associated with each of the models.

Abstract: Configurations herein provide a language processing mechanism operable to define a machine vocabulary and identify a machine language version of the words that preserves context and identifies the proper definition of the words by identifying and preserving context of a particular set of words, such as a sentence or paragraph. The machine vocabulary includes a definition section for each definition of a word. Each definition section includes a set of one or more definition elements. The definition elements include a predetermined format of definition fields, and each has a corresponding mask indicative of significant definition fields. The set of definition elements corresponding to a particular definition describe the usage of the word in a context matching that particular definition. Each definition element captures a characteristic of the definition according to fuzzy logic such that the definition elements collectively capture the context.

Abstract: Certain aspects and embodiments of the present invention are directed to systems and methods for monitoring and analyzing the language environment and the development of a key child. A key child's language environment and language development can be monitored without placing artificial limitations on the key child's activities or requiring a third party observer. The language environment can be analyzed to identify words, vocalizations, or other noises directed to or spoken by the key child, independent of content. The analysis can include the number of responses between the child and another, such as an adult and the number of words spoken by the child and/or another, independent of content of the speech. One or more metrics can be determined based on the analysis and provided to assist in improving the language environment and/or tracking language development of the key child.

Abstract: A system for use in speech recognition includes an acoustic module accessing a plurality of distinct-language acoustic models, each based upon a different language; a lexicon module accessing at least one lexicon model; and a speech recognition output module. The speech recognition output module generates a first speech recognition output using a first model combination that combines one of the plurality of distinct-language acoustic models with the at least one lexicon model. In response to a threshold determination, the speech recognition output module generates a second speech recognition output using a second model combination that combines a different one of the plurality of distinct-language acoustic models with the at least one distinct-language lexicon model.

Abstract: There is provided a voice activity detection method for indicating an active voice mode and an inactive voice mode. The method comprises receiving a first portion of an input signal; determining that the first portion of the input signal includes an active voice signal; indicating the active voice mode in response to the determining that the first portion of the input signal includes the active voice signal; receiving a second portion of the input signal immediately following the first portion of the input signal; determining that the second portion of the input signal includes an inactive voice signal; extending the indicating the active voice mode for a period of time after determining that the second portion of the input signal includes the inactive voice signal, wherein the period of time varies based on one or more conditions; and indicating the inactive voice mode after expiration of the period of time.

Abstract: A system includes an acoustic input engine configured to accept a speech input, to recognize phonemes of the speech input, and to create word strings based on the recognized phonemes. The system includes a semantic engine coupled to the acoustic engine and operable to identify actions and to identify objects by parsing the word strings. The system also includes an action-object pairing system to identify a dominant entry from the identified actions and the identified objects, to select a complement to the dominant entry from the identified actions and the identified objects, and to form an action-object pair that includes the dominant entry and the complement. The system further includes an action-object routing table operable to provide a routing destination based on the action-object pair. The system also includes a call routing module to route a call to the routing destination.

Abstract: In one embodiment, the present invention is directed to reconfiguration of a communication device or other network node based on a determination that a user has a target (altered) physical condition.

Abstract: In one embodiment, the present invention is directed to a communication device that analyzes received utterances and detects when the speaker has a target physical condition.

Abstract: Systems and techniques for analyzing voice recognition results in order to improve efficiency and accuracy of voice recognition. When a voice activated module undertakes a voice recognition attempt, it invokes a voice recognition module that constructs a list of voice recognition results. The list is analyzed by a results postprocessor that employs information relating to past recognition results and user information to make changes to the list. The results postprocessor may delete results that have been previously rejected during a current recognition transaction and may further alter and reorder the results list based on historical results. The results postprocessor may further alter and reorder the results list based on information relating to the user engaging in the recognition attempt.

Abstract: Configurations herein provide a language processing mechanism operable to define a machine vocabulary and identify a machine language version of the words that preserves context and identifies the proper definition of the words by identifying and preserving context of a particular set of words, such as a sentence or paragraph. The machine vocabulary includes a definition section for each definition of a word. Each definition section includes a set of one or more definition elements. The definition elements include a predetermined format of definition fields, and each has a corresponding mask indicative of significant definition fields. The set of definition elements corresponding to a particular definition describe the usage of the word in a context matching that particular definition. Each definition element captures a characteristic of the definition according to fuzzy logic such that the definition elements collectively capture the context.

Abstract: A method and apparatus for normalizing a histogram utilizing a backward cumulative histogram which can cumulate a probability distribution function in an order from a greatest to smallest value so as to estimate a noise robust histogram. A method of normalizing a speech feature vector includes: extracting the speech feature vector from a speech signal; calculating a probability distribution function using the extracted speech feature vector; calculating a backward cumulative distribution function by cumulating the probability distribution function in an order from a largest to smallest value; and normalizing a histogram using the backward cumulative distribution function.

Abstract: An audio input signal is filtered using an adaptive filter to generate a prediction output signal with reduced noise, wherein the filter is implemented using a plurality of coefficients to generate a plurality of prediction errors and to generate an error from the plurality of prediction errors, wherein the absolute values of the coefficients are continuously reduced by a plurality of reduction parameters.

Abstract: A method and apparatus for indexing one or more audio signals using a speech to text engine and a phoneme detection engine, and generating a combined lattice comprising a text part and a phoneme part. A word to be searched is searched for in the text part, and if not found, or is found with low certainty is divided into phonemes and searched for in the phoneme parts of the lattice.

Abstract: A system and method are disclosed for switching contexts within a spoken dialog between a user and a spoken dialog system. The spoken dialog system utilizes modular subdialogs that are invoked by at least one flow controller that is a finite state model and that associated with a dialog manager. The spoken dialog system includes a dialog manager with a flow controller and a reusable subdialog module. The method includes, while the spoken dialog is being controlled by the subdialog module that was invoked by the flow controller, receiving context-changing input associated with speech from a user that changes a dialog context and comparing the context-changing input to at least one context shift. And, if any of the context shifts are activated by the comparing step, then passing control of the spoken dialog to the flow controller with context shift message and destination state.

Abstract: A system for implementing voice services can include at least one virtual machine, such as a Java 2 Enterprise Edition (J2EE) virtual machine. The virtual machine can include a bean container for handling software beans, such as Enterprise Java Beans. The bean container can include a voice browser bean. The voice browser bean can include a VoiceXML browser.

Abstract: Systems and techniques for improved user prompting. A system according to one aspect of the invention includes a central server hosting various modules providing services to users. The modules suitably employ voice recognition in order to interpret user inputs. Each module has access to user information that includes information indicating the user's experience with each function of each module. When a module needs to issue a prompt to the user, it retrieves and examines the user information to determine the user's experience with the module and function. Suitably, each module is operative to categorize a user as belonging to an experience category, such as novice, intermediate and expert based on the user's level of experience with the function. The module selects a prompt associated with the user's level of experience with the function and presents it to the user.

Abstract: Embodiments of a localization system are disclosed. In one embodiment, a plurality of localization components provide localized data that is localized to one or more distinct markets. A translation matching component receives a localization request corresponding to input data to be localized. The translation matching component accesses the plurality of localization components based on the localization request. The translation matching component selects and outputs localized data from one or more of the plurality of localization components based on pre-determined criteria. In one embodiment, the translation matching component selects the localized data based on a time required to obtain the localized data. In another embodiment, the localization components provide confidence scores associated with the localized data, the translation matching component selecting the localized data based on the confidence scores.

Abstract: The present invention overcomes problems of tandem coding method such as degradation of speech quality, increased system latency and computations. An apparatus for trans-coding between code excited linear prediction (CELP) type codecs with different bandwidths, includes: a format parameter translating unit for generating output formant parameters by translating formant parameters from input CELP format to output CELP format; a formant parameter quantizing unit for receiving the output format formant parameters and quantizing the output format formant filter coefficients; an excited parameter translating unit for generating output excitation parameters by translating excitation parameters from input CELP format to output CELP format; and an excitation quantizing unit for receiving the output format excitation parameters and quantizing the output format excitation parameters.

Abstract: A method of training language model parameters trains discriminative model parameters in the language model based on a performance measure having discrete values.